Encode big-endian numbers with a byte swap instead of std::reverse

write_number() reordered multi-byte numbers for the big-endian formats
(CBOR/MessagePack/UBJSON) with std::reverse over the byte array. GCC
lowered only some sizes to a bswap; clang kept a scalar byte shuffle
(0 bswap instructions in the CBOR number path). Replace the reverse with
size-dispatched __builtin_bswap16/32/64 helpers (portable shift fallback
for other compilers; std::reverse retained for exotic sizes such as a
long double number_float_t).

Codegen: the CBOR number path now emits bswap on both compilers
(gcc 2 -> 16, clang 0 -> 4). Output is byte-for-byte identical to the
previous implementation across the binary differential corpus.

Throughput (isolated vs the std::reverse version, best of 9):
  CBOR int64 array   gcc +7%   clang +10%
  CBOR uint16 array  gcc +27%  clang flat

Modest but consistent on number-dense encodings; negligible on
string/blob-heavy output, as expected.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01XAYM1qhSA2FDaDcGfPW3fG
Signed-off-by: Niels Lohmann <mail@nlohmann.me>

include/nlohmann/detail/output/output_adapters.hpp

@@ -13,6 +13,7 @@
 #include <iterator> // back_inserter
 #include <memory> // shared_ptr, make_shared
 #include <string> // basic_string
+#include <utility> // move
 #include <vector> // vector
 
 #ifndef JSON_NO_IO
@@ -118,6 +119,72 @@ class output_string_adapter : public output_adapter_protocol<CharType>
     StringType& str;
 };
 
+/// @brief non-virtual output sink writing into a std::vector
+///
+/// Unlike output_vector_adapter, this sink is not part of the virtual
+/// output_adapter_protocol hierarchy: it is passed to binary_writer by value as
+/// a template parameter, so write_character()/write_characters() are ordinary
+/// (inlinable) calls with no vtable lookup and no shared_ptr. It is used for the
+/// common `to_cbor`/`to_msgpack`/... into a std::vector.
+template<typename CharType, typename AllocatorType = std::allocator<CharType>>
+class output_vector_sink
+{
+  public:
+    explicit output_vector_sink(std::vector<CharType, AllocatorType>& vec) noexcept
+        : v(vec)
+    {}
+
+    void write_character(CharType c)
+    {
+        v.push_back(c);
+    }
+
+    // no JSON_HEDLEY_NON_NULL here: binary_writer legitimately passes a null
+    // pointer with length 0 for empty strings/binary values. Appending an empty
+    // range is a no-op; the type-erased path tolerates this via the (unattributed)
+    // virtual base, and the concrete sink must do the same.
+    void write_characters(const CharType* s, std::size_t length)
+    {
+        v.insert(v.end(), s, s + length);
+    }
+
+  private:
+    std::vector<CharType, AllocatorType>& v;
+};
+
+/// @brief output sink forwarding to a type-erased output adapter
+///
+/// Wraps the polymorphic output_adapter_t so the same binary_writer template can
+/// also target arbitrary adapters (output streams, strings, user-provided
+/// adapters) via the `output_adapter`-based overloads. Each write still goes
+/// through one virtual call, exactly as before; only the concrete sinks above
+/// avoid it.
+template<typename CharType>
+class output_adapter_sink
+{
+  public:
+    explicit output_adapter_sink(output_adapter_t<CharType> adapter)
+        : oa(std::move(adapter))
+    {
+        JSON_ASSERT(oa);
+    }
+
+    void write_character(CharType c)
+    {
+        oa->write_character(c);
+    }
+
+    // no JSON_HEDLEY_NON_NULL: forwards (null, 0) for empty payloads, exactly as
+    // the type-erased path already did before this sink existed
+    void write_characters(const CharType* s, std::size_t length)
+    {
+        oa->write_characters(s, length);
+    }
+
+  private:
+    output_adapter_t<CharType> oa = nullptr;
+};
+
 template<typename CharType, typename StringType = std::basic_string<CharType>>
 class output_adapter
 {

include/nlohmann/json.hpp

@@ -140,7 +140,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
     friend ::nlohmann::detail::serializer<basic_json>;
     template<typename BasicJsonType>
     friend class ::nlohmann::detail::iter_impl;
-    template<typename BasicJsonType, typename CharType>
+    template<typename BasicJsonType, typename CharType, typename OutputSinkType>
     friend class ::nlohmann::detail::binary_writer;
     template<typename BasicJsonType, typename InputType, typename SAX>
     friend class ::nlohmann::detail::binary_reader;
@@ -4327,7 +4327,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
     static std::vector<std::uint8_t> to_cbor(const basic_json& j)
     {
         std::vector<std::uint8_t> result;
-        to_cbor(j, result);
+        detail::binary_writer<basic_json, std::uint8_t, detail::output_vector_sink<std::uint8_t>>(
+            detail::output_vector_sink<std::uint8_t>(result)).write_cbor(j);
         return result;
     }
 
@@ -4350,7 +4351,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
     static std::vector<std::uint8_t> to_msgpack(const basic_json& j)
     {
         std::vector<std::uint8_t> result;
-        to_msgpack(j, result);
+        detail::binary_writer<basic_json, std::uint8_t, detail::output_vector_sink<std::uint8_t>>(
+            detail::output_vector_sink<std::uint8_t>(result)).write_msgpack(j);
         return result;
     }
 
@@ -4375,7 +4377,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
             const bool use_type = false)
     {
         std::vector<std::uint8_t> result;
-        to_ubjson(j, result, use_size, use_type);
+        detail::binary_writer<basic_json, std::uint8_t, detail::output_vector_sink<std::uint8_t>>(
+            detail::output_vector_sink<std::uint8_t>(result)).write_ubjson(j, use_size, use_type);
         return result;
     }
 
@@ -4403,7 +4406,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
             const bjdata_version_t version = bjdata_version_t::draft2)
     {
         std::vector<std::uint8_t> result;
-        to_bjdata(j, result, use_size, use_type, version);
+        detail::binary_writer<basic_json, std::uint8_t, detail::output_vector_sink<std::uint8_t>>(
+            detail::output_vector_sink<std::uint8_t>(result)).write_ubjson(j, use_size, use_type, true, true, version);
         return result;
     }
 
@@ -4430,7 +4434,8 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
     static std::vector<std::uint8_t> to_bson(const basic_json& j)
     {
         std::vector<std::uint8_t> result;
-        to_bson(j, result);
+        detail::binary_writer<basic_json, std::uint8_t, detail::output_vector_sink<std::uint8_t>>(
+            detail::output_vector_sink<std::uint8_t>(result)).write_bson(j);
         return result;
     }